---

Friday, January 13, 2006. IIIT Hyderabad

---

Industrial Sessions : 14:00 to 15:30

Special Talk : 16:00 to 17:00
"Factorization Methods in Computer Vision"
Prof. Takeo Kanade, Carnegie Mellon University

Welcome reception: 19:00 to 21:00
Venue: IIIT Hyderabad
Sponsored by : IBM IRL, New Delhi

---

Saturday, January 14, 2006. Hotel Taj Krishna

---

Inauguration: 08:30AM

Plenary Talk 1: 9:00 to 10:00.
Prof. Andrew Blake, Microsoft Research

Oral session S1: 10:00 to 11:00
Oral session S2A & S2B: 11:40 to 13:00
Poster session 1: 14:00 to 16:00
Oral Session S3A & S3B: 16:00 to 18:00

---

Sunday, January 15, 2006. Hotel Taj Krishna

---

Plenary Talk 2: 08:30 to 09:40
Prof. Andrew Zisserman, Oxford

Oral session S4: 09:40 to 11:00
Oran session S5A & S5B: 11:40 to 13:00
Poster session 2: 14:00 to 16:00
Oral Session S6A & S6B: 16:00 to 18:00

Conference banquet: 19:00 to 22:00
Venue: Rock Heights, Shilparamam

Special program : Drums of Kerala
By Naveena Samskarika Kala Kendram

Sponsored by : Satyam Computers, Hyderabad

---

Monday, January 16, 2006. Hotel Taj Krishna

---

Plenary Talk 3: 08:30 to 09:40.
Prof. Baba Vemuri, Univ of Florida

Oral session 7: 09:40 to 11:00
Oral session S8A & S8B: 11:30 to 13:10
Poster session 3: 14:00 to 16:00
Oral Session 9: 16:00 to 17:00
Close of the conference

---

14:00 - 15:30 Industrial Sessions (WCVGIP) Seminar Hall


16:00 - 17:00 Special Talk Seminar Hall
Introduced by Narendra Ahuja, UIUC/IIIT

Factorization Methods in Computer Vision
Takeo Kanade, Carnegie Mellon University


17:00 - 19:30 Indian Vision Showcase


19:30 onwards Welcome Reception Guest House







8:30 - 9:00 Inauguration Grand Ball Room (A) & (B)

9:00 - 10:00 Plenary Talk 1 Grand Ball Room (A) & (B)
Introduced by Harry Shum, Microsoft Research Asia

Video Segmentation by Fusion of Colour, Contrast and Stereo
Prof. Andrew Blake, Microsoft Research, Cambridge

Abstract
Technology advances mean that a stereo webcam could be manufactured and sold for essentially the same price as a monocular one. There are two outstanding advantages for teleconferencing in using stereo vision. First, automatic control of pan/tilt/zoom, which is possible monocularly, is particularly robust in stereo. Second privacy can be protected by obscuring background elements and replacing them with safer ones. For example a business conversation held at home could show only the talking head, against a bland video background, with inappropriate elements obscured. The first of these advantages is readily attainable and we describe progress towards achieving the second.

An algorithm will be described that is capable of real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from colour/contrast or from stereo alone is known to be error-prone. Here, colour,contrast and stereo matching information are fused to infer layers accurately and efficiently. The "Layered Graph Cut" algorithm does not directly solve stereo. Instead it marginalises the stereo match likelihood over foreground and background hypotheses, and fuses it with a contrast-sensitive colour model that is learned on the fly. Segmentation is then solved efficiently and exactly by binary graph cut. The algorithm will be demonstrated in the application of background substitution and shown to give good quality composite video output.



10:00 - 11:00 S1: Camera Calibration Grand Ball Room (A) & (B)
Chair : Subhashis Banerjee

S1-1

On Using Silhouettes for Camera Calibration
Edmond Boyer

S1-2

Towards a Guaranteed Solution to Plane-Based Self-calibration
Benoît Bocquillon, Pierre Gurdjos, Alain Crouzil

S1-3

Plane-Based Calibration and Auto-calibration of a Fish-Eye Camera
Hongdong Li, Richard Hartley

11:00 - 11:40 Coffee Break

11:40 - 13:00 S2A: Stereo and Pose Grand Ball Room (A)
Chair : Larry Davis

S2A-1

Stereo Matching Using Iterated Graph Cuts and Mean Shift Filtering
Ju Yong Chang, Kyoung Mu Lee, Sang Uk Lee

S2A-2

Augmented Stereo Panoramas
Chien-Wei Chen, Li-Wei Chan, Yu-Pao Tsai, Yi-Ping Hung

S2A-3

A Local Basis Representation for Estimating Human Pose from Cluttered Images
Ankur Agarwal, Bill Triggs

S2A-4

Alignment of 3D Models to Images Using Region-Based Mutual Information and Neighborhood Extended Gaussian Images
Hon-Keat Pong, Tat-Jen Cham

11:40 - 13:00 S2B: Texture Grand Ball Room (B)
Chair : Uday B. Desai

S2B-1

The Eigen-Transform and Applications
Alireza Tavakoli Targhi, Eric Hayman, Jan-Olof Eklundh, Mehrdad Shahshahani

S2B-2

Edge-Model Based Representation of Laplacian Subbands
Malay K. Nema, Subrata Rakshit

S2B-3

Fusion of Texture Variation and On-Line Color Sampling for Moving Object Detection Under Varying Chromatic Illumination
Chunfeng Shen, Xueyin Lin, Yuanchun Shi

S2B-4

Combining Microscopic and Macroscopic Information for Rotation and Histogram Equalization Invariant Texture
S. Liao, W.K. Law, Albert C.S. Chung

13:00 - 14:00 Lunch

14:00 - 16:00 Poster Session 1-A Pearl Room (B)

PS1-1

Shift-Invariant Image Denoising Using Mixture of Laplace Distributions in Wavelet-Domain
B.S. Raghavendra, P. Subbanna Bhat

PS1-2

Blind Watermarking Via Pixel Modification with Regular Rule
Yulin Wang, Jinxu Guo

PS1-3

Surface Interpolation by Adaptive Neuro-fuzzy Inference System Based Local Ordinary Kriging
Coskun Özkan

PS1-4

Texture Image Segmentation: An Interactive Framework Based on Adaptive Features and Transductive Learning
Shiming Xiang, Feiping Nie, Changshui Zhang

PS1-5

Image Segmentation That Merges Together Boundary and Region Information
Wei Wang, Ronald Chung

PS1-6

Extraction of Main Urban Roads from High Resolution Satellite Images by Machine
Yanqing Wang, Yuan Tian, Xianqing Tai, Lixia Shu

PS1-7

Texture Classification Using a Novel, Soft-Set Theory Based Classification Algorithm
Milind M. Mushrif, S. Sengupta, A.K. Ray

PS1-8

Extrinsic Camera Parameter Estimation Based-on Feature Tracking and GPS Data
Yuji Yokochi, Sei Ikeda, Tomokazu Sato, Naokazu Yokoya

PS1-9

A Method for Calibrating a Motorized Object Rig
Pang-Hung Huang, Yu-Pao Tsai, Wan-Yen Lo, Sheng-Wen Shih, Chu-Song Chen, Yi-Ping Hung

PS1-10

Calibration of Rotating Line Camera for Spherical Imaging
Tomoyuki Hirota, Hajime Nagahara, Masahiko Yachida

PS1-11

An Efficient Real Time Low Bit Rate Video Codec
Shikha Tripathi, R. Vikas, R.C. Jain

PS1-12

Semi-metric Space: A New Approach to Treat Orthogonality and Parallelism
Jun-Sik Kim, In So Kweon

14:00 - 16:00 Poster Session 1-B Grand Ball Room (C)

PS1-13

Gaussian Decomposition for Robust Face Recognition
Fumihiko Sakaue, Takeshi Shakunaga

PS1-14

Occlusion Invariant Face Recognition Using Selective LNMF Basis Images
Hyun Jun Oh, Kyoung Mu Lee, Sang Uk Lee, Chung-Hyuk Yim

PS1-15

Two-Dimensional Fisher Discriminant Analysis and Its Application to Face Recognition
Zhizheng Liang, Pengfei Shi, David Zhang

PS1-16

Combining Geometric and Gabor Features for Face Recognition
P.S. Hiremath, Ajit Danti

PS1-17

Complex Activity Representation and Recognition by Extended Stochastic Grammar
Zhang Zhang, Kaiqi Huang, Tieniu Tan

PS1-18

Recognize Multi-people Interaction Activity by PCA-HMMs
Ying Wang, Xinwen Hou, Tieniu Tan

PS1-19

Object Recognition Through the Principal Component Analysis of Spatial Relationship Amongst Lines
B.H. Shekar, D.S. Guru, P. Nagabhushan

PS1-20

PCA-Based Recognition for Efficient Inpainting
Thommen Korah, Christopher Rasmussen

PS1-21

Learning Multi-category Classification in Bayesian Framework
Atul Kanaujia, Dimitris Metaxas

PS1-22

Estimation of Structural Information Content in Images
Subrata Rakshit, Anima Mishra

PS1-23

Automatic Moving Object Segmentation with Accurate Boundaries
Jia Wang, Haifeng Wang, Qingshan Liu, Hanqing Lu

PS1-24

A Bottom up Algebraic Approach to Motion Segmentation
Dheeraj Singaraju, René Vidal

PS1-25

A Multiscale Co-linearity Statistic Based Approach to Robust Background Modeling
Prithwijit Guha, Dibyendu Palai, K.S. Venkatesh, Amitabha Mukerjee

PS1-26

Motion Detection in Driving Environment Using U-V-Disparity
Jia Wang, Zhencheng Hu, Hanqing Lu, Keiichi Uchimura

PS1-27

Visual Surveillance Using Less ROIs of Multiple Non-calibrated Cameras
Takashi Nishizaki, Yoshinari Kameda, Yuichi Ohta

PS1-28

Employing a Fish-Eye for Scene Tunnel Scanning
Jiang Yu Zheng, Shigang Li

PS1-29

A Novel Robust Statistical Method for Background Initialization and Visual Surveillance
Hanzi Wang, David Suter

PS1-30

Exemplar-Based Human Contour Tracking
Shiming Xiang, Feiping Nie, Changshui Zhang

PS1-31

Tracking Targets Via Particle Based Belief Propagation
Jianru Xue, Nanning Zheng, Xiaopin Zhong

PS1-32

Multiple-Person Tracking Using a Plan-View Map with Error Estimation
Kentaro Hayashi, Takahide Hirai, Kazuhiko Sumi, Koichi Sasakawa

PS1-33

Viewpoint Determination of Image by Interpolation over Sparse Samples
Bodong Liang, Ronald Chung

PS1-34

Inverse Volume Rendering Approach to 3D Reconstruction from Multiple Images
Shuntaro Yamazaki, Masaaki Mochimaru, Takeo Kanade

PS1-35

Gaze Direction Estimation with a Single Camera Based on Four Reference Points and Three Calibration Images
Shinjiro Kawato, Akira Utsumi, Shinji Abe

PS1-36

3D Shape Recovery of Smooth Surfaces: Dropping the Fixed Viewpoint Assumption
Yael Moses, Ilan Shimshoni

PS1-37

Stereo Matching by Interpolation
Bodong Liang, Ronald Chung

PS1-38

Novel View Synthesis Using Locally Adaptive Depth Regularization
Hitesh Shah, Subhasis Chaudhuri

PS1-39

View Synthesis of Scenes with Multiple Independently Translating Objects from Uncalibrated Views
Geetika Sharma, Santanu Chaudhury, J.B. Srivastava

PS1-40

Generating Free Viewpoint Images from Mutual Projection of Cameras
Koichi Kato, Jun Sato

PS1-41

Video Synthesis with High Spatio-temporal Resolution Using Motion Compensation and Image Fusion in Wavelet Domain
Kiyotaka Watanabe, Yoshio Iwai, Hajime Nagahara, Masahiko Yachida, Toshiya Suzuki

PS1-42

Estimating Illumination Parameters in Real Space with Application to Image Relighting
Feng Xie, Linmi Tao, Guangyou Xu, Huijun Di

PS1-43

Automatically Building 2D Statistical Shapes Using the Topology Preservation Model GNG
José García Rodríguez, Anastassia Angelopoulou, Alexandra Psarrou, Kenneth Revett

16:00 - 18:00 S3A: Face Recognition Grand Ball Room (A)
Chair : Tanveer Syeda Mehmood

S3A-1

Boosting Multi-gabor Subspaces for Face Recognition
QingShan Liu, HongLiang Jin, XiaoOu Tang, HanQing Lu, SongDe Ma

S3A-2

A New Distance Criterion for Face Recognition Using Image Sets
Tat-Jun Chin, David Suter

S3A-3

Face-Voice Authentication Based on 3D Face Models
Girija Chetty, Michael Wagner

S3A-4

Face Recognition Under Varying Illumination Based on MAP Estimation Incorporating Correlation Between Surface Points
Mihoko Shimano, Kenji Nagao, Takahiro Okabe, Imari Sato, Yoichi Sato

S3A-5

Exploring Facial Expression Effects in 3D Face Recognition
Yueming Wang, Gang Pan, Zhaohui Wu, Yigang Wang

S3A-6

Vision Based Speech Animation Transferring with Underlying Anatomical Structure
Yuru Pei, Hongbin Zha

16:00 - 18:00 S3B: Variational Methods Grand Ball Room (B)
Chair : Prem Kalra

S3B-1

A Level Set Approach for Shape Recovery of Open Contours
Min Li, Chandra Kambhamettu, Maureen Stone

S3B-2

Statistical Shape Models Using Elastic-String Representations
Anuj Srivastava, Aastha Jain, Shantanu Joshi, David Kaziska

S3B-3

Minimal Weighted Local Variance as Edge Detector for Active Contour Models
W.K. Law, Albert C.S. Chung

S3B-4

Online Updating Appearance Generative Mixture Model for Meanshift Tracking
Jilin Tu, Hai Tao, Thomas Huang

S3B-5

Dynamic Open Contours Using Particle Swarm Optimization with Application to Fluid Interface Extraction
M. Thomas, S.K. Misra, C. Kambhamettu, J.T. Kirby

S3B-6

Attractor-Guided Particle Filtering for Lip Contour Tracking
Yong-Dian Jian, Wen-Yan Chang, Chu-Song Chen

8:30 - 9:40 Plenary Talk 2 Grand Ball Room (A) & (B)
Introduced by Takeo Kanade, CMU


Category Recognition: Bags of Words and Beyond
Prof. Andrew Zisserman, Oxford University

Abstract
There has been much recent research activity - and much recent success - in recognizing visual object categories (such as cars, faces, motorbikes) in images. The success has come from representing objects by sets of local iconic image patches, where each patch may be thought of as a "visual word" for describing part of the object. Surprisingly object categories can be recognized without including the spatial organization/location of the patches, and these models are referred to as a "bag of words" in analogy with similar models in the statistical text understanding literature.

In this talk I will describe two methods for learning bag of words models: an unsupervised approach where object category models are learnt from an unlabelled set of images; and a supervised approach where object category models are learnt from images obtained from Google image search. In both cases object category models are obtained by fitting with probabilistic Latent Semantic Analysis (pLSA), a model originally developed in the statistical text literature. The talk will conclude with some illustrations of how spatial organization can be added to these models.




9:40 - 11:00 S4: Tracking Grand Ball Room
Chair : Subhasis Chaudhuri

S4-1

Tracking with the Kinematics of Extremal Contours
David Knossow, Rémi Ronfard, Radu Horaud, Frédéric Devernay

S4-2

Multiregion Level Set Tracking with Transformation Invariant Shape Priors
Michael Fussenegger, Rachid Deriche, Axel Pinz

S4-3

Multi-view Object Tracking Using Sequential Belief Propagation
Wei Du, Justus Piater

S4-4

Dense Motion and Disparity Estimation Via Loopy Belief Propagation
Michael Isard, John MacCormick

11:00 - 11:40 Coffee Break

11:40 - 13:00 S5A: Geometry and Calibration Grand Ball Room (A)
Chair : Yi-Ping Hung

S5A-1

Theory and Calibration for Axial Cameras
Srikumar Ramalingam, Peter Sturm, Suresh K. Lodha

S5A-2

Error Characteristics of SFM with Erroneous Focal Length
Loong-Fah Cheong, Xu Xiang

S5A-3

Interpreting Sphere Images Using the Double-Contact Theorem
Xianghua Ying, Hongbin Zha

S5A-4

New 3D Fourier Descriptors for Genus-Zero Mesh Objects
Hongdong Li, Richard Hartley

11:40 - 13:00 S5B: Lighting and Focus Grand Ball Room (B)
Chair : Rin-Ichiro Taniguchi

S5B-1

High Dynamic Range Global Mosaic
Dae-Woong Kim, Ki-Sang Hong

S5B-2

Image-Based Calibration of Spatial Domain Depth-from-Defocus and Application to Automatic Focus Tracking
Soon-Yong Park, Jaekyoung Moon

S5B-3

Effects of Image Segmentation for Approximating Object Appearance Under Near Lighting
Takahiro Okabe, Yoichi Sato

S5B-4

Fast Feature Extraction Using Approximations to Derivatives with Summed-Area Images
Paul Wyatt, Hiroaki Nakai

13:00 - 14:00 Lunch


14:00 - 16:00 Poster Session 2-A Pearl Room (B)

PS2-1

Fast Approximated SIFT
Michael Grabner, Helmut Grabner, Horst Bischof

PS2-2

Image Matching by Multiscale Oriented Corner Correlation
Feng Zhao, Qingming Huang, Wen Gao

PS2-3

Fisheye Lenses Calibration Using Straight-Line Spherical Perspective Projection Constraint
Xianghua Ying, Zhanyi Hu, Hongbin Zha

PS2-4

Robust Linear Auto-calibration of a Moving Camera from Image Sequences
Thorsten Thormählen, Hellward Broszio, Patrick Mikulastik

PS2-5

Super-Resolved Video Mosaicing for Documents Based on Extrinsic Camera Parameter Estimation
Akihiko Iketani, Tomokazu Sato, Sei Ikeda, Masayuki Kanbara, Noboru Nakajima, Naokazu Yokoya

PS2-6

Frame Rate Stabilization by Variable Resolution Shape Reconstruction for On-Line Free-Viewpoint Video Generation
Rui Nabeshima, Megumu Ueda, Daisaku Arita, Rin-ichiro Taniguchi

PS2-7

Content Based Image and Video Retrieval Using Embedded Text
Chinmaya Misra, Shamik Sural

PS2-8

FormPad: A Camera-Assisted Digital Notepad
Tanveer Syeda-Mahmood, Thomas Zimmerman

PS2-9

A Geometric Contour Framework with Vector Field Support
Zhenglong Li, Qingshan Liu, Hanqing Lu

PS2-10

Clustering Spherical Shells by a Mini-Max Information Algorithm
Xulei Yang, Qing Song, Wenbo Zhang, Zhimin Wang

PS2-11

Clustering of Interval-Valued Symbolic Patterns Based on Mutual Similarity Value and the Concept of k-Mutual Nearest Neighborhood
D.S. Guru, H.S. Nagendraswamy

PS2-12

Multiple Similarities Based Kernel Subspace Learning for Image Classification
Wang Yan, Qingshan Liu, Hanqing Lu, Songde Ma

14:00 - 16:00 Poster Session 2-B Grand Ball Room (C)

PS2-13

Detecting Faces from Low-Resolution Images
Shinji Hayashi, Osamu Hasegawa

PS2-14

Human Distribution Estimation
Akira Utsumi, Hirotake Yamazoe, Ken-ichi Hosaka, Seiji Igi

PS2-15

Modelling the Effect of View Angle Variation on Appearance-Based Gait Recognition
Shiqi Yu, Daoliang Tan, Tieniu Tan

PS2-16

Gesture Recognition Using Quadratic Curves
Qiulei Dong, Yihong Wu, Zhanyi Hu

PS2-17

From Motion Patterns to Visual Concepts for Event Analysis in Dynamic Scenes
Lun Xin, Tieniu Tan

PS2-18

Probabilistic Modeling for Structural Change Inference
Wei Liu, Véronique Prinet

PS2-19

Robust Occluded Shape Recognition
Ronak Shah, Anima Mishra, Subrata Rakshit

PS2-20

Interactive Contour Extraction Using NURBS-HMM
Debin Lei, Chunhong Pan, Qing Yang, Minyong Shi

PS2-21

Learning Parameter Tuning for Object Extraction
Xiongcai Cai, Arcot Sowmya, John Trinder

PS2-22

Region-Level Motion-Based Foreground Detection with Shadow Removal Using MRFs
Shih-Shinh Huang, Li-Chen Fu, Pei-Yung Hsiao

PS2-23

Waterfall Segmentation of Complex Scenes
Allan Hanbury, Beatriz Marcotegui

PS2-24

Markovian Framework for Foreground-Background-Shadow Separation of Real World Video Scenes
Csaba Benedek, Tamás Szirányi

PS2-25

Separation of Reflection and Transparency Using Epipolar Plane Image Analysis
Thanda Oo, Hiroshi Kawasaki, Yutaka Ohsawa, Katsushi Ikeuchi

PS2-26

Surface Registration Using Extended Polar Maps
Elsayed E. Hemayed

PS2-27

Multiple Range Image Registration by Matching Local Log-Polar Range Images
Takeshi Masuda

PS2-28

Incremental Mesh-Based Integration of Registered Range Images: Robust to Registration Error and Scanning Noise
Hong Zhou, Yonghuai Liu, Longzhuang Li

PS2-29

Infinite Homography Estimation Using Two Arbitrary Planar Rectangles
Jun-Sik Kim, In So Kweon

PS2-30

Shape Orientability
Joviša Zunic, Paul L. Rosin, Lazar Kopanja

PS2-31

How to Compute the Pose of an Object Without a Direct View?
Peter Sturm, Thomas Bonfort

PS2-32

A New Active Contour Model: Curvature Gradient Vector Flow
Jifeng Ning, Chengke Wu, Shigang Liu, Peizhi Wen

PS2-33

A Real-Time Large Disparity Range Stereo-System Using FPGAs
Divyang K. Masrani, W. James MacLean

PS2-34

Use of a Dense Surface Point Distribution Model in a Three-Stage Anatomical Shape Reconstruction from Sparse Information for Computer Assisted Orthopaedic Surgery: A Preliminary Study
Guoyan Zheng, Kumar T. Rajamani, Lutz-Peter Nolte

PS2-35

Vision-Based Posing of 3D Virtual Actors
Ameya S.Vaidya, Appu Shaji, Sharat Chandran

PS2-36

Object Tracking Using Background Subtraction and Motion Estimation in MPEG Videos
Ashwani Aggarwal, Susmit Biswas, Sandeep Singh, Shamik Sural, A.K. Majumdar

PS2-37

Multi-camera Tracking of Articulated Human Motion Using Motion and Shape Cues
Aravind Sundaresan, Rama Chellappa

PS2-38

Matching Gait Image Sequences in the Frequency Domain for Tracking People at a Distance
Ryusuke Sagawa, Yasushi Makihara, Tomio Echigo, Yasushi Yagi

PS2-39

Performance Evaluation of Object Detection and Tracking in Video
Vasant Manohar, Padmanabhan Soundararajan, Harish Raju, Dmitry Goldgof, Rangachar Kasturi, John Garofolo

PS2-40

Vehicle Detection Using Double Slit Camera
Shunji Katahara, Masayoshi Aoki

PS2-41

Automatic Vehicle Detection Using Statistical Approach
Chi-Chen Raxle Wang, Jenn-Jier James Lien

PS2-42

A Handheld Projector Supported by Computer Vision
Akash Kushal, Jeroen van Baar, Ramesh Raskar, Paul Beardsley

PS2-43

Symmetric Color Ratio in Spiral Architecture
Wenjing Jia, Huaifeng Zhang, Xiangjian He, Qiang Wu

16:00 - 18:00 S6A: Detection and Applications Grand Ball Room (A)
Chair : David Suter

S6A-1

Boosted Algorithms for Visual Object Detection on Graphics Processing Units
Hicham Ghorayeb, Bruno Steux, Claude Laurgeau

S6A-2

Combining Iterative Inverse Filter with Shock Filter for Baggage Inspection Image Deblurring
Guoqiang Yu, Jin Zhang, Li Zhang, Zhiqiang Chen, Yuanjing Li

S6A-3

Automatic Chromosome Classification Using Medial Axis Approximation and Band Profile Similarity
Jau Hong Kao, Jen Hui Chuang, Tsai Pei Wang

S6A-4

Object Detection Using a Cascade of 3D Models
Hon-Keat Pong, Tat-Jen Cham

S6A-5

Heuristic Pre-clustering Relevance Feedback in Region-Based Image Retrieval
Wan-Ting Su, Wen-Sheng Chu, Jenn-Jier James Lien

S6A-6

Biologically Motivated Perceptual Feature: Generalized Robust Invariant Feature
Sungho Kim, In So Kweon

16:00 - 18:00 Statistics and Kernels Grand Ball Room (B)
Chair : Chandra Kambhamettu

S6B-1

A Framework for 3D Object Recognition Using the Kernel Constrained Mutual Subspace Method
Kazuhiro Fukui, Björn Stenger, Osamu Yamaguchi

S6B-2

An Iterative Method for Preserving Edges and Reducing Noise in High Resolution Image Reconstruction
Chanho Jung, Gyeonghwan Kim

S6B-3

Fast Binary Dilation/Erosion Algorithm Using Kernel Subdivision
Ajay Narayanan

S6B-4

Fast Global Motion Estimation Via Iterative Least-Square Method
Jia Wang, Haifeng Wang, Qingshan Liu, Hanqing Lu

S6B-5

Kernel-Based Robust Tracking for Objects Undergoing Occlusion
R. Venkatesh Babu, Patrick Perez, Patrick Bouthemy

S6B-6

Adaptive Object Tracking with Online Statistical Model Update
KaiYeuh Chang, Shang-Hong Lai

19:00 onwards

Conference Banquet
Rock Heights,   Shilparamam  

Special Program : Drums of Kerala
by Naveena Samskarika Kala Kendram

Sponsored by : Satyam Computers, Hyderabad

January 16, 2006 (Monday)

8:30 - 9:40 Plenary Talk 3 Grand Ball Room (A) & (B)
Introduced by Katsushi Ikeuchi


Information Theoretic Measures and Their Applications to Computer Vision and Medical Imaging
Prof. Baba C Vemuri, University of Florida

Abstract
Information theory has played a fundamental role in many fields of science and engineering including Computer Vision and Medical Imaging. In this talk, I will introduce various information theoretic measures that are used in achieving the goal of solving several important problems in Computer Vision and Medical Imaging, namely, image registration, point set registration, tensor field segmentation, image/shape retrieval etc. Recently introduced information theoretic measures such as, entropy defined on distributions, averages of Gaussian distributions (computed as the minimizer of the sum of squared J-divergences) and the well known Jensen-Shannon divergence etc. will be presented. I will show how each of these measures are used in solving the aforementioned application problems. The talk will be interspersed with several examples from each of the aforementioned applications.

9:40 - 11:00 S7: Segmentation Grand Ball Room (A) & (B)
Chair : Santanu Chaudhury

S7-1

Inducing Semantic Segmentation from an Example
Yaar Schnitman, Yaron Caspi, Daniel Cohen-Or, Dani Lischinski

S7-2

Super Resolution Using Graph-Cut
Uma Mudenagudi, Ram Singla, Prem Kalra, Subhashis Banerjee

S7-3

A Multiphase Level Set Based Segmentation Framework with Pose Invariant Shape Priors
Michael Fussenegger, Rachid Deriche, Axel Pinz

S7-4

A Unified Framework for Segmentation-Assisted Image Registration
Jundong Liu, Yang Wang, Junhong Liu

11:30 - 13:10 S8A: Geometry and Statistics Grand Ball Room (A)
Chair : Hiroshi Murase

S8A-1

Fusion of 3D and Appearance Models for Fast Object Detection and Pose Estimation
Hesam Najafi, Yakup Genc, Nassir Navab

S8A-2

Efficient 3D Face Reconstruction from a Single 2D Image by Combining Statistical and Geometrical Information
Shu-Fan Wang, Shang-Hong Lai

S8A-3

Multiple View Geometry in the Space-Time
Kazutaka Hayakawa, Jun Sato

S8A-4

Detecting Critical Configuration of Six Points
Yihong Wu, Zhanyi Hu

S8A-5

Robustness in Motion Averaging
Venu Madhav Govindu

11:30 - 13:10 S8B: Signal Processing Grand Ball Room (B)

Chair : Yaser Yacoob

S8B-1

Detection of Moving Objects by Independent Component Analysis
Masaki Yamazaki, Gang Xu, Yen-Wei Chen

S8B-2

OK-Quantization Theory and Its Relationship to Sampling Theorem
Yuji Tanaka, Takayuki Fujiwara, Hiroyasu Koshimizu, Taizo Iijima

S8B-3

Contour Matching Based on Belief Propagation
Shiming Xiang, Feiping Nie, Changshui Zhang

S8B-4

Key Frame-Based Activity Representation Using Antieigenvalues
Naresh P. Cuntoor, Rama Chellappa

S8B-5

Fast Image Replacement Using Multi-resolution Approach
Chih-Wei Fang, Jenn-Jier James Lien

13:00 - 14:00 Lunch


14:00 - 16:00 Poster Session 3A Pearl Room (B)

PS3-1

Classification of Photometric Factors Based on Photometric Linearization
Yasuhiro Mukaigawa, Yasunori Ishii, Takeshi Shakunaga

PS3-2

Material Classification Using Morphological Pattern Spectrum for Extracting Textural Features from Material Micrographs
D. Ghosh, David C. Tou Wei<;

PS3-3

Identification of Printing Process Using HSV Colour Space
Haritha Dasari, Chakravarthy Bhagvati

PS3-4

Fast Block Matching Algorithm in Walsh Hadamard Domain
Ngai Li, Chun-Man Mak, Wai-Kuen Cham

PS3-5

Skin Detection by Near Infrared Multi-band for Driver Support System
Yasuhiro Suzuki, Kazuhiko Yamamoto, Kunihito Kato, Michinori Andoh, Shinichi Kojima

PS3-6

Virtual Fashion Show Using Real-Time Markerless Motion Capture
Ryuzo Okada, Björn Stenger, Tsukasa Ike, Nobuhiro Kondoh

PS3-7

Dense 3D Reconstruction with an Uncalibrated Active Stereo System
Hiroshi Kawasaki, Yutaka Ohsawa, Ryo Furukawa, Yasuaki Nakamura

PS3-8

Surface-Independent Direct-Projected Augmented Reality
Hanhoon Park, Moon-Hyun Lee, Sang-Jun Kim, Jong-Il Park

PS3-9

Aspects of Optimal Viewpoint Selection and Viewpoint Fusion
Frank Deinzer, Joachim Denzler, Christian Derichs, Heinrich Niemann

PS3-10

An Efficient Approach for Multi-view Face Animation Based on Quasi 3D Model
Yanghua Liu, Guangyou Xu, Linmi Tao

PS3-11

Hallucinating 3D Faces
Shiqi Peng, Gang Pan, Shi Han, Yueming Wang

PS3-12

High Quality Compression of Educational Videos Using Content-Adaptive Framework
Ankush Mittal, Ankur Jain, Sourabh Jain, Sumit Gupta

14:00 - 16:00 Poster Session 3B Grand Ball Room (C)

PS3-13

Histogram Features-Based Fisher Linear Discriminant for Face Detection
Haijing Wang, Peihua Li, Tianwen Zhang

PS3-14

Perception Based Lighting Balance for Face Detection
Xiaoyue Jiang, Pei Sun, Rong Xiao, Rongchun Zhao

PS3-15

An Adaptive Weight Assignment Scheme in Linear Subspace Approaches for Face Recognition
Satyanadh Gundimada, Vijayan Asari

PS3-16

Template-Based Hand Pose Recognition Using Multiple Cues
Björn Stenger

PS3-17

Scalable Representation and Learning for 3D Object Recognition Using Shared Feature-Based View Clustering
Sungho Kim, In So Kweon

PS3-18

Video Scene Interpretation Using Perceptual Prominence and Mise-en-scène Features
Gaurav Harit, Santanu Chaudhury

PS3-19

Smooth Foreground-Background Segmentation for Video Processing
Konrad Schindler, Hanzi Wang

PS3-20

Efficient Object Segmentation Using Digital Matting for MPEG Video Sequences
Yao-Tsung Jason Tsai, Jenn-Jier James Lien

PS3-21

Background Segmentation Beyond RGB
Fredrik Kristensen, Peter Nilsson, Viktor Öwall

PS3-22

A Hierarchical Framework for Generic Sports Video Classification
Maheshkumar H. Kolekar, Somnath Sengupta

PS3-23

Feature Detection with an Improved Anisotropic Filter
Mohamed Gobara, David Suter

PS3-24

Feature Selection for Image Categorization
Feng Xu, Yu-Jin Zhang

PS3-25

An Energy Minimization Process for Extracting Eye Feature Based on Deformable Template
Huachun Tan, Yu-Jin Zhang

PS3-26

Image Feature Detection as Robust Model Fitting
Dengfeng Chai, Qunsheng Peng

PS3-27

Spatiotemporal Density Feature Analysis to Detect Liver Cancer from Abdominal CT Angiography
Yoshito  Mekada, Yuki  Wakida, Yuichiro  Hayashi, Ichiro  Ide, Hiroshi~Murase

PS3-28

Extraction of Salient Contours Via Excitatory-Inhibitory Interactions in the Visual Cortex
Qiling Tang, Nong Sang, Tianxu Zhang

PS3-29

Extracting Surface Representations from Rim Curves
Hai Chen, Kwan-Yee K. Wong, Chen Liang, Yue Chen

PS3-30

Applying Non-stationary Noise Estimation to Achieve Contrast Invariant Edge Detection
Paul Wyatt, Hiroaki Nakai

PS3-31

Corner Detection Using Morphological Skeleton: An Efficient and Nonparametric Approach
R. Dinesh, D.S. Guru

PS3-32

Correspondence Search in the Presence of Specular Highlights Using Specular-Free Two-Band Images
Kuk-Jin Yoon, In-So Kweon

PS3-33

Stereo Matching Algorithm Using a Weighted Average of Costs Aggregated by Various Window Sizes
Kan'ya Sasaki, Seiji Kameda, Atsushi Iwata

PS3-34

Pseudo Measurement Based Multiple Model Approach for Robust Player Tracking
Xiaopin Zhong, Nanning Zheng, Jianru Xue

PS3-35

A Hierarchical Method for 3D Rigid Motion Estimation
Thitiwan Srinark, Chandra Kambhamettu, Maureen Stone

PS3-36

Space-Time Invariants for 3D Motions from Projective Cameras
Ying Piao, Jun Sato

PS3-37

Detecting and Tracking Distant Objects at Night Based on Human Visual System
Kaiqi Huang, Liangsheng Wang, Tieniu Tan

PS3-38

Motion Guided Video Sequence Synchronization
Daniel Wedge, Du Huynh, Peter Kovesi

PS3-39

Landmark Based Global Self-localization of Mobile Soccer Robots
Abdul Bais, Robert Sablatnig

PS3-40

Self-calibration Based 3D Information Extraction and Application in Broadcast Soccer Video
Yang Liu, Dawei Liang, Qingming Huang, Wen Gao

PS3-41

Error Analysis of SFM Under Weak-Perspective Projection
Loong-Fah Cheong, Shimiao Li

PS3-42

General Specular Surface Triangulation
Thomas Bonfort, Peter Sturm, Pau Gargallo

16:00 - 17:00 S9: Video Processing Grand Ball Room (A) & (B)
Chair : Arun Pujari

S9-1

Double Regularized Bayesian Estimation for Blur Identification in Video Sequences
Hongwei Zheng, Olaf Hellwich

S9-2

A Multi-Layer MRF Model for Video Object Segmentation
Zoltan Kato, Ting-Chuen Pong

S9-3

Scene Interpretation: Unified Modeling of Visual Context by Particle-based Belief Propagation in Hierarchical Graphical Model
Sungho Kim, In So Kweon

---

---